多模态大模型论文趋势 2023–2026
视觉语言模型、图像/视频理解与生成式多模态基础模型
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 11,209 篇被归入该主题的论文。
主要结论
- 多模态大模型论文从 2023 年的 1,226 篇增长到 2026 年的 5,192 篇，三年间扩大到约 4.2 倍。
- NeurIPS 是发多模态大模型论文最多的会议，2023–2026 年共 3,319 篇，占四个会议总量的 30%。
- 交叉方向里涨得最快的是应用 · computer vision：同时属于两个主题的论文从 2023 年的 35 篇增至 2026 年的 596 篇。
- 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 1；同组增长最快的AI 智能体是 12 倍，多模态大模型是 4.2 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 433 | 138 | 146 | 509 | 1,226 |
| 2024 | 446 | 321 | 323 | 626 | 1,716 |
| 2025 | 1,074 | 816 | 390 | 795 | 3,075 |
| 2026 | 1,366 | 1,401 | 1,051 | 1,374 | 5,192 |
代表论文
按年份和会议均匀挑选，方便快速看到每一届的样貌
- NeurIPS 2026$\text{A}^3$-VLA: Automatic Perception-Guided Attention Alignment for Robot Manipulation
- ICML 2026[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation
- ICLR 2026A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic
- CVPR 20263D Space as a Scratchpad for Editable Text-to-Image Generation
- NeurIPS 2025$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
- ICML 2025Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation
- ICLR 2025$\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models
- CVPR 20252DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification
- NeurIPS 2024A Concept-Based Explainability Framework for Large Multimodal Models
- ICML 2024A Multimodal Automated Interpretability Agent
- ICLR 2024Alt-Text with Context: Improving Accessibility for Images on Twitter
- CVPR 2024Data-Efficient Multimodal Fusion on a Single GPU
- NeurIPS 20234M: Massively Multimodal Masked Modeling
- ICML 2023$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
- ICLR 2023A Primal-Dual Framework for Transformers and Neural Networks
- CVPR 20233D Concept Learning and Reasoning From Multi-View Images
- NeurIPS 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
- ICML 2026$G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA
- ICLR 2026A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models
- CVPR 20263D-IDE 3D Implicit Depth Emergent
全部多模态大模型论文
共 1,074 篇，第 21 / 22 页
- NeurIPS 2025Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2
- NeurIPS 2025VCM: Vision Concept Modeling with Adaptive Vision Token Compression via Instruction Fine-Tuning
- NeurIPS 2025VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models
- NeurIPS 2025VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR
- NeurIPS 2025ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
- NeurIPS 2025Vid-SME: Membership Inference Attacks against Large Video Understanding Models
- NeurIPS 2025VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models
- NeurIPS 2025Video Perception Models for 3D Scene Synthesis
- NeurIPS 2025Video-R1: Reinforcing Video Reasoning in MLLMs
- NeurIPS 2025Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs
- NeurIPS 2025VideoCAD: A Dataset and Model for Learning Long‑Horizon 3D CAD UI Interactions from Video
- NeurIPS 2025VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception
- NeurIPS 2025VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance
- NeurIPS 2025VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
- NeurIPS 2025VideoLucy: Deep Memory Backtracking for Long Video Understanding
- NeurIPS 2025VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
- NeurIPS 2025VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
- NeurIPS 2025VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
- NeurIPS 2025Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
- NeurIPS 2025VisDiff: SDF-Guided Polygon Generation for Visibility Reconstruction, Characterization and Recognition
- NeurIPS 2025Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
- NeurIPS 2025Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation
- NeurIPS 2025Vision Function Layer in Multimodal LLMs
- NeurIPS 2025Vision Transformers Don't Need Trained Registers
- NeurIPS 2025Vision Transformers with Self-Distilled Registers
- NeurIPS 2025Vision-centric Token Compression in Large Language Model
- NeurIPS 2025Vision‑Language‑Vision Auto‑Encoder: Scalable Knowledge Distillation from Diffusion Models
- NeurIPS 2025VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
- NeurIPS 2025ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
- NeurIPS 2025ViSPLA: Visual Iterative Self-Prompting for Language-Guided 3D Affordance Learning
- NeurIPS 2025Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection
- NeurIPS 2025Visual Instruction Bottleneck Tuning
- NeurIPS 2025Visual Structures Help Visual Reasoning: Addressing the Binding Problem in LVLMs
- NeurIPS 2025Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought
- NeurIPS 2025VisualLens: Personalization through Task-Agnostic Visual History
- NeurIPS 2025VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
- NeurIPS 2025VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction-Editing Data and Long Captions
- NeurIPS 2025VITRIX-UniViTAR: Unified Vision Transformer with Native Resolution
- NeurIPS 2025VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
- NeurIPS 2025VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
- NeurIPS 2025VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
- NeurIPS 2025VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models
- NeurIPS 2025VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron Chunking
- NeurIPS 2025VLM-R³: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
- NeurIPS 2025VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture
- NeurIPS 2025VLMs can Aggregate Scattered Training Patches
- NeurIPS 2025VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs
- NeurIPS 2025VMDT: Decoding the Trustworthiness of Video Foundation Models
- NeurIPS 2025Vocabulary-Guided Gait Recognition
- NeurIPS 2025VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查多模态大模型在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "multimodal-llms"}
常见问题
- 2023–2026 年四大会议一共有多少篇多模态大模型论文？
- 共 11,209 篇，按年份分别是 2023 年 1,226 篇、2024 年 1,716 篇、2025 年 3,075 篇、2026 年 5,192 篇。
- NeurIPS 2026 有多少篇多模态大模型论文？
- NeurIPS 2026 有 1,366 篇多模态大模型论文，上一届是 1,074 篇。
- ICLR 2026 有多少篇多模态大模型论文？
- ICLR 2026 有 1,401 篇多模态大模型论文，上一届是 816 篇。
- ICML 2026 有多少篇多模态大模型论文？
- ICML 2026 有 1,051 篇多模态大模型论文，上一届是 390 篇。
- CVPR 2026 有多少篇多模态大模型论文？
- CVPR 2026 有 1,374 篇多模态大模型论文，上一届是 795 篇。
- 哪个会议的多模态大模型论文最多？
- NeurIPS，2023–2026 年共 3,319 篇。